OpenAI: GPT-6.1 Terra
LiveOpenAI1.1M context · Text, Vision, Tools, ReasoningBenchmark price · $1 input / $5 output per 1M tokens
Best discount now97.0%offYou pay 3.0% of reference.
Median discount35.5%offAcross 34 live offers.
Realized · 7 days62.4%avgRequest-weighted average.
Requests · 24h5,13534 offers from 25 sellers.
Current offers
34 of 52 offers
Availability
Providers
ProviderDiscountPriceLatencyUptimeCacheSold
OpenAI
87%
$0.13 in
$0.65 out
3.0s
59.3%
93.2%
-
OpenAI
87%
$0.13 in
$0.65 out
3.0s
59.3%
93.2%
-
Total
Cumulative offers
Sold
$18
Discount trend
Realized · 7 days97.6%
Best, twice dailyMedian 35.5%
Recent fills
10:5122 tokensInferHub95.2%
10:5115 tokensOpenAI direct48.4%
10:5126 tokensOpenAI direct48.8%
10:5030 tokensInferHub96.3%
10:5015 tokensOpenAI direct48.4%
10:4015 tokensOpenAI direct48.4%
10:4022 tokensInferHub95.2%
10:3817 tokensOpenAI direct49.1%
10:3543,953 tokensInferHub96.9%
10:3540,603 tokensInferHub96.9%
10:3437,969 tokensInferHub96.9%
10:3437,940 tokensInferHub96.9%
10:3237,472 tokens96.9%
10:3237,363 tokensInferHub96.9%
10:3237,229 tokensInferHub96.9%
10:3015 tokensOpenAI direct48.4%
10:2949 tokensVenice AI17.7%
10:2922 tokensInferHub95.2%
10:28542 tokensOpenAI direct50.0%
10:2736,798 tokensInferHub96.9%
Times in UTCSettled on Base in USDC.
Performance by provider route · 24h
Measured on Surplus traffic| Route | p50 latency | p95 latency | Throughput | Success rate | ShareShare of traffic |
|---|---|---|---|---|---|
| OpenRouter | 5.55 s | 13.64 s | 73 tok/s | 98.9% | 42% |
| OpenAI direct | 4.11 s | 13.64 s | 73 tok/s | 59.3% | 38% |
| InferHub | 111.50 s | 203.21 s | 30 tok/s | 26.0% | 20% |
OpenRouter42% of traffic
98.9% success
OpenAI direct38% of traffic
59.3% success
InferHub20% of traffic
26.0% success
Use this modelChange your base URL.
Change your base URL.
Keep your code.
Any OpenAI-compatible client works. Add /min30 to the path to only buy at 30% off or better.
Read the quickstart ↗Parameters this model acceptsPOST /v1/chat/completions
- modelstringThis model’s id
- messagesarrayThe conversation, as role and content pairs
- streambooleanSend the answer as server-sent events
- max_tokensintegerMost output tokens to generate
- seedintegerDeterministic sampling
- toolsarrayFunctions the model may call, in the OpenAI format
- tool_choicestring | objectauto, required, none, or one named function
- response_formatobjectJSON mode or a JSON schema for structured output
- structured_outputsbooleanAccepts a JSON schema in response_format
- reasoning_effortstringHow hard to think, as a string such as "high"
- reasoningobjectReasoning options as an object, such as {"effort": "high"}
- include_reasoningbooleanStripped before the request reaches the provider
- verbosity
Context window 1.1M tokens · Max output 128K tokensOthers are passed through; most providers ignore what they don’t support. Parameter compatibility ↗
from openai import OpenAI client = OpenAI( api_key="inf_your_key_here", base_url="$SURPLUS_BASE_URL" ) response = client.chat.completions.create( model="gpt-6.1-terra", messages=[{"role": "user", "content": "Hello!"}] )
SURPLUS_BASE_URL
https://api.surplusintelligence.ai/v1